A Benchmarking Framework for AI models in Automotive Aerodynamics

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Tangsali, Kaustubh, Ranade, Rishikesh, Nabian, Mohammad Amin, Kamenev, Alexey, Sharpe, Peter, Ashton, Neil, Cherukuri, Ram, Choudhry, Sanjay
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915389966909440
author Tangsali, Kaustubh
Ranade, Rishikesh
Nabian, Mohammad Amin
Kamenev, Alexey
Sharpe, Peter
Ashton, Neil
Cherukuri, Ram
Choudhry, Sanjay
author_facet Tangsali, Kaustubh
Ranade, Rishikesh
Nabian, Mohammad Amin
Kamenev, Alexey
Sharpe, Peter
Ashton, Neil
Cherukuri, Ram
Choudhry, Sanjay
contents In this paper, we introduce a benchmarking framework within the open-source NVIDIA PhysicsNeMo-CFD framework designed to systematically assess the accuracy, performance, scalability, and generalization capabilities of AI models for automotive aerodynamics predictions. The open extensible framework enables incorporation of a diverse set of metrics relevant to the Computer-Aided Engineering (CAE) community. By providing a standardized methodology for comparing AI models, the framework enhances transparency and consistency in performance assessment, with the overarching goal of improving the understanding and development of these models to accelerate research and innovation in the field. To demonstrate its utility, the framework includes evaluation of both surface and volumetric flow field predictions on three AI models: DoMINO, X-MeshGraphNet, and FIGConvNet using the DrivAerML dataset. It also includes guidelines for integrating additional models and datasets, making it extensible for physically consistent metrics. This benchmarking study aims to enable researchers and industry professionals in selecting, refining, and advancing AI-driven aerodynamic modeling approaches, ultimately fostering the development of more efficient, accurate, and interpretable solutions in automotive aerodynamics
format Preprint
id arxiv_https___arxiv_org_abs_2507_10747
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Benchmarking Framework for AI models in Automotive Aerodynamics
Tangsali, Kaustubh
Ranade, Rishikesh
Nabian, Mohammad Amin
Kamenev, Alexey
Sharpe, Peter
Ashton, Neil
Cherukuri, Ram
Choudhry, Sanjay
Machine Learning
In this paper, we introduce a benchmarking framework within the open-source NVIDIA PhysicsNeMo-CFD framework designed to systematically assess the accuracy, performance, scalability, and generalization capabilities of AI models for automotive aerodynamics predictions. The open extensible framework enables incorporation of a diverse set of metrics relevant to the Computer-Aided Engineering (CAE) community. By providing a standardized methodology for comparing AI models, the framework enhances transparency and consistency in performance assessment, with the overarching goal of improving the understanding and development of these models to accelerate research and innovation in the field. To demonstrate its utility, the framework includes evaluation of both surface and volumetric flow field predictions on three AI models: DoMINO, X-MeshGraphNet, and FIGConvNet using the DrivAerML dataset. It also includes guidelines for integrating additional models and datasets, making it extensible for physically consistent metrics. This benchmarking study aims to enable researchers and industry professionals in selecting, refining, and advancing AI-driven aerodynamic modeling approaches, ultimately fostering the development of more efficient, accurate, and interpretable solutions in automotive aerodynamics
title A Benchmarking Framework for AI models in Automotive Aerodynamics
topic Machine Learning
url https://arxiv.org/abs/2507.10747